Google Tesseract: Optical Character Recognition (OCR) on HDD / SSD Labels Using Machine Vision

This paper is designed to have an optical character recognition system capable of interpreting captured images of hard disk drive and solid-state drive labels with high accuracy. Manual checking of the disk capacity size and part number found on the labels is time consuming, more prone to errors and utilizes more manpower. Automating the inspection through optical character recognition using image pre-processing and machine vision contributes to an easier inspection process, better management of records and faster cycle time. The images captured using a vision camera went through different stages of image pre-processing via OpenCV-Python and recognition through Google Tesseract. Different categorical variables including exposure time and location of texts in a captured image were used to determine and improve the overall recognition accuracy. By improving the lighting condition through the addition of light sources, the developed OCR system was able to achieve a character recognition accuracy of 99.375%.